GPT-3是文化遗产视觉问答的全部所需吗？
Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?
AI总结：
本文提出一种基于GPT-3的视觉问答方法，通过运行时生成艺术品描述单，完全避免图像和专家标注过程，并评估了描述生成质量及视觉问答性能。
摘要：
近年来，深度学习和计算机视觉在文化遗产领域的应用日益增多，涵盖音频智能导览、互动博物馆和增强现实。这些技术需要大量数据才能有效运作并为用户提供价值。在艺术品领域，此类数据由专家进行标注，过程昂贵且耗时。具体而言，为执行视觉问答等常见任务，需收集每件艺术品的图像及其描述单。本文提出一种视觉问答方法，可在运行时生成描述单，用于回答关于艺术品的视觉与语境问题，从而完全避免图像和标注过程。为此，我们研究使用GPT-3生成艺术品描述，并通过字幕生成指标分析生成描述的质量。最后，我们评估了视觉问答和字幕生成任务的性能。
英文摘要：
The use of Deep Learning and Computer Vision in the Cultural Heritage domain is becoming highly relevant in the last few years with lots of applications about audio smart guides, interactive museums and augmented reality. All these technologies require lots of data to work effectively and be useful for the user. In the context of artworks, such data is annotated by experts in an expensive and time consuming process. In particular, for each artwork, an image of the artwork and a description sheet have to be collected in order to perform common tasks like Visual Question Answering. In this paper we propose a method for Visual Question Answering that allows to generate at runtime a description sheet that can be used for answering both visual and contextual questions about the artwork, avoiding completely the image and the annotation process. For this purpose, we investigate on the use of GPT-3 for generating descriptions for artworks analyzing the quality of generated descriptions through captioning metrics. Finally we evaluate the performance for Visual Question Answering and captioning tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
